A biomechanical model of mammographic compressions

Abstract

A number of biomechanical models have been proposed to improve nonrigid registration techniques for multimodal breast image alignment. A deformable breast model may also be useful for overcoming difficulties in interpreting 2D X-ray projections (mammograms) of 3D volumes (breast tissues). If a deformable model could accurately predict the shape changes that breasts undergo during mammography, then the model could serve to localize suspicious masses (visible in mammograms) in the unloaded state, or in any other deformed state required for further investigations (such as biopsy or other medical imaging modalities). In this paper, we present a validation study that was conducted in order to develop a biomechanical model based on the well-established theory of continuum mechanics (finite elasticity theory with contact mechanics) and demonstrate its use for this application. Experimental studies using gel phantoms were conducted to test the accuracy in predicting mammographic-like deformations. The material properties of the gel phantom were estimated using a nonlinear optimization process, which minimized the errors between the experimental and the model-predicted surface data by adjusting the parameter associated with the neo-Hookean constitutive relation. Two compressions (the equivalent of cranio-caudal and medio-lateral mammograms) were performed on the phantom, and the corresponding deformations were recorded using a MRI scanner. Finite element simulations were performed to mimic the experiments using the estimated material properties with appropriate boundary conditions. The simulation results matched the experimental recordings of the deformed phantom, with a sub-millimeter root-mean-square error for each compression state. Having now validated our finite element model of breast compression, the next stage is to apply the model to clinical images.

Three-dimensional computer generated breast phantom based on empirical data

“…Deformable biomechanical breast models [104][105][106][107][108]. Finite element analysis is commonly used to determine the stresses and displacements in mechanical objects and systems.…”

“…Several of the aforementioned patient-specific biomechanical breast models have been developed to simulate compression and are able to predict the compressed location of registration markers to less than 5mm [73,86,104,106,107,110,113,[115][116][117][118][119][120]. Most of these models have been optimized to yield results in a clinically-relevant timeframe (<30 minutes) but tend to utilize relatively coarse meshes (node spacing on the order of centimeters) to decrease computational time at the expense of spatial resolution.…”

“…Unfortunately, there are difficulties measuring the stress-strain relationship of breast tissues accurately because the mechanical properties are dependent on the in situ environment of the tissue and the mechanical measurement technique (i.e., static vs. dynamic). Consequently, there are a wide range of values for the elastic modulus of different breast tissues used in current biomechanical models [73,86,104,106,107,110,113,[115][116][117][118][119][120]124]: adipose tissue ranges from 0.5 to 25 kPa, glandular tissue from 0.08 to 272 kPa, and skin from 0.088 to 3 MPa. For our analysis, changing the separate tissues' Young's moduli relative to one another was parametrically studied to determine the impact on the simulated tissue compression (Table 4-1).…”

“…Other groups have used registration markers and the outline of the breast in a real mammogram to evaluate the accuracy of the simulated compression [104,106,107,110,[115][116][117][118][119][120]. However, since we are using the simulated compression as part of a breast phantom package, it was superfluous to evaluate the accuracy of the simulated compression.…”

Finite-element modeling of compression and gravity on a population of breast phantoms for multimodality imaging simulation

“…15,24 Other studies have also included the effects of gravity. 9,21,22,25 Current state-of-the-art methods often optimize the initial breast position 16 and/or material parameters [16][17][18]20 through a FE-registration framework. Registrations, between breast MR images at different levels of compression, have also been used to provide boundary constraints to define the displacement of the region posterior to the compression plates in a corresponding FE model.…”